Machine Learning Applications on Agricultural Datasets for Smart Farm Enhancement



Download 2,12 Mb.
Pdf ko'rish
bet19/29
Sana27.09.2022
Hajmi2,12 Mb.
#850453
1   ...   15   16   17   18   19   20   21   22   ...   29
Bog'liq
machines-06-00038

Italian Province
Prediction Error—Apple
Prediction Error—Pears
NN
LR
NN
LR
Udine
6.10%
25.50%
3.53%
14.19%
Gorizia
12.72%
45.56%
6.64%
16.33%
Trieste
21.80%
21.25%
9.83%
21.25%
Pordenone
12.04%
38.47%
154.79%
153.12%
L’Aquila
0.05%
0.06%
0.04%
0.08%
Teramo
2.52%
2.53%
1.52%
13.03%
Pescara
3.74%
5.45%
10.52%
19.17%
Chieti
3.65%
10.54%
2.26%
2.73%
Cosenza
22.68%
63.79%
16.57%
20.62%
Catanzaro
8.23%
21.12%
2.97%
55.93%
Reggio Calabria
11.38%
42.60%
6.14%
13.08%
Crotone
7.00%
95.57%
7.46%
133.60%
Vibo Valentia
7.50%
27.55%
29.40%
45.31%
Mean
9.19%
30.77%
19.36%
39.11%


Machines
2018
,
6
, 38
14 of 22
As the Istat dataset features huge and complete time-series with which the neural network model
results best fit the predictive task; in Table
5
, there are the predicted and real values for the total crops of
L’Aquila province and real values are very near to the predicted ones, in fact for apples the difference is
less than 2% and for pears less than 4.5%, highlighting the goodness of using this technique on this type
of dataset.
Table 5.
Task 1: a comparison example between the real values and their neural network model
prediction for the apple and pear total crops for the Italian province of L’Aquila on the Istat dataset.
Method: NN
Apple
Pears
Italian Province
Real Value
Predicted Value
Real Value
Predicted Value
L’Aquila
45,900
45,000
3925
3750
3.2. Task 2—Comparison between Machine Learning Algorithms on Missing Data (CNR Dataset—Results)
For this task, the predictive errors depicted in Table
6
highlight that the polynomial model best fits
the LAI values prediction for the three considered cultures. This outcome can be explained considering the
nature of this scientific values, as well as the temporal discontinuity with which they have been gathered,
along with their small amount; for the polynomial model, there is a very large difference from the others,
highlighting the simplicity and the advantage of using this standard but also the performing technique.
The plot comparison between linear and polynomial predictive models on this scientific dataset
is in Figure
7
, where a polynomial interpolation (green plot) shows how the predictive model is able
to approximate the peculiar growing trend (blue plot), which can fit unknown incoming data very
well. The higher grade mathematical model is better than the others and this happens both if, for the
training, you give the data for a single year, either if you give data for three years.
Table 6.
Task 2: comparison on the prediction error for the cultures leaf area index (LAI) value
exploiting machine learning methods on the CNR scientific agrarian dataset.
Culture
Prediction Error
NN
LR
Polynomial
Artichokes
139.00%
101.63%
25.70%
Pear
1779.38%
81.80%
10.00%
Pacciamata Eggplant
933.10%
564.89%
6.26%
Machines 
2018

6
, x FOR PEER REVIEW
14 of 22 
As the Istat dataset features huge and complete time-series with which the neural network 
model results best fit the predictive task; in Table 5, there are the predicted and real values for the 
total crops of L’Aquila province and real values are very near to the predicted ones, in fact for apples 
the difference is less than 2% and for pears less than 4.5%, highlighting the goodness of using this 
technique on this type of dataset. 
Table 5.
Task 1: a comparison example between the real values and their neural network model 
prediction for the apple and pear total crops for the Italian province of L’Aquila on the Istat dataset. 

Download 2,12 Mb.

Do'stlaringiz bilan baham:
1   ...   15   16   17   18   19   20   21   22   ...   29




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©hozir.org 2024
ma'muriyatiga murojaat qiling

kiriting | ro'yxatdan o'tish
    Bosh sahifa
юртда тантана
Боғда битган
Бугун юртда
Эшитганлар жилманглар
Эшитмадим деманглар
битган бодомлар
Yangiariq tumani
qitish marakazi
Raqamli texnologiyalar
ilishida muhokamadan
tasdiqqa tavsiya
tavsiya etilgan
iqtisodiyot kafedrasi
steiermarkischen landesregierung
asarlaringizni yuboring
o'zingizning asarlaringizni
Iltimos faqat
faqat o'zingizning
steierm rkischen
landesregierung fachabteilung
rkischen landesregierung
hamshira loyihasi
loyihasi mavsum
faolyatining oqibatlari
asosiy adabiyotlar
fakulteti ahborot
ahborot havfsizligi
havfsizligi kafedrasi
fanidan bo’yicha
fakulteti iqtisodiyot
boshqaruv fakulteti
chiqarishda boshqaruv
ishlab chiqarishda
iqtisodiyot fakultet
multiservis tarmoqlari
fanidan asosiy
Uzbek fanidan
mavzulari potok
asosidagi multiservis
'aliyyil a'ziym
billahil 'aliyyil
illaa billahil
quvvata illaa
falah' deganida
Kompyuter savodxonligi
bo’yicha mustaqil
'alal falah'
Hayya 'alal
'alas soloh
Hayya 'alas
mavsum boyicha


yuklab olish